Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/rul1an/assay/agents-mdgit clone --depth 1 https://github.com/Rul1an/assayWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/rul1an/assay/agents-md)<a href="https://agentmods.dev/instructions/rul1an/assay/agents-md"><img src="https://agentmods.dev/badge/instructions/rul1an/assay/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.02320 | $0.02320 |
| Opus 5 | $0.01160 | $0.01160 |
| Sonnet 5 | $0.00464 | $0.00464 |
| Haiku 4.5 | $0.00232 | $0.00232 |
Grade A, and why
assay AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assay Agent Contract
This file is the shared operating contract for Codex, Claude Code, Cursor, and automated PR reviewers. Tool-specific instruction files may add mechanics, but they must not restate or weaken this contract.
Canonical State
- Repository truth is the checked-in code and documentation.
- The public execution ledger for the active programme is named on this line: issue #2764.
- Keep the number to the ledger line; everywhere else the contract names the role, so the next programme costs one edit here rather than one in every section. Name the new ledger there when one opens, and say so plainly there when none is active. Nothing enforces that, so it is an instruction and not a guarantee — and the way it fails is quiet: the line kept pointing at a finished programme, which reads as an active ledger and sends handoffs to a closed issue.
- Agent chats, local plans, memories, and unpushed branches are not authoritative project state.
- Every handoff for a programme slice records the branch, PR, exact head SHA, verification, reviews, non-claims, and open findings in that programme's ledger. Work outside a programme — a standalone fix, a documentation change — has no ledger to record to, and inventing one or appending to a closed one is worse than the omission.
ADR-042/043 Scope
Read these before changing evidence ingestion, evidence verification, or MCP authorization:
The ADR-042 stop list is normative:
- no scalar trust score;
- no whole-action verdict;
- no generic agent identity, delegation, or federation layer;
- no provider-outcome verification;
- no detector catalogue or broad MCP scan;
- no compliance or safe-agent claim;
- no certification or partnership status without a checkable basis.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed · -1 lines · -23 tokens per session 14bef8d43368
- 4d ago First seen · 174 lines · 2,343 tokens per session scan A b2fb44ef2e57
assay AGENTS.md is an instructions file published in the GitHub repository Rul1an/assay (9 stars, last pushed today), licensed MIT. It adds 2,320 tokens to every session, about $0.0116 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
toolhive-studio copilot-instructions.md
Copilot instructions for stacklok/toolhive-studio, covering instructions for copilot, ui components, data fetching, file naming conventions and testing.
toolhive-studio CLAUDE.md
Claude Code instructions for stacklok/toolhive-studio, covering project overview, build and development commands, environment requirements, common gotchas and auto-generated code — never edit manually.
toolhive-studio AGENTS.md
AGENTS.md instructions for stacklok/toolhive-studio, covering project overview, essential commands, common gotchas, boundaries and code conventions.
agent-security-scanner-mcp CLAUDE.md
Claude Code instructions for sinewaveai/agent-security-scanner-mcp, covering claude.md, build and development commands, install dependencies, run all tests (28 test files, 420+ tests, 4.5 min) and run specific test file.
org-mcp-server copilot-instructions.md
Copilot instructions for szaffarano/org-mcp-server, covering org-mcp-server, working effectively, bootstrap and build, development commands and validation.
org-mcp-server CLAUDE.md
Claude Code instructions for szaffarano/org-mcp-server, covering claude.md, project overview, development commands, just commands (available in nix devshell) and architecture.